Hire an AI quarterly product roadmap planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• An opportunity tree: the customer problems under each outcome, each with its evidence
• An outcome roadmap with a measure, an owner and bets under each outcome
• A list of old roadmap features that have no outcome behind them
• A quarter plan with the bets, what each should move, how you will know and what you are not doing
• A one-page update for stakeholders

How it does the job well

• Start from the user problem and the evidence for it, then the solution.
• Write decisions down with the reason and the options you rejected.
• Keep scope small enough to ship and learn. Name what is out of scope.
• Define how success will be measured before building.

Mistakes it avoids

• Writing a feature list and calling it outcomes.
• Opportunities taken from the old roadmap instead of from customer evidence.
• Bets with no number that should move.
• Squeezing too many bets into the quarter instead of cutting.
• Treating opinions or one loud request as proven demand.
• Specs that skip edge cases, error states or dependencies.

What a good result looks like

An example, not your task: Your roadmap has twenty features and no one can say what each is for.

• Opportunity tree. For each outcome, the customer problems that would move its number, each with evidence and solution ideas.
• Outcome roadmap. Each outcome with its measure, owner and bets, plus a list of old features that have no outcome.
• Quarter plan. The bets that fit your capacity, what each should move, how you will know and what you are not doing.
• Stakeholder update. A one-page note on outcomes, bets, what changed since last time and what you are not doing.
• Hand-back summary. Each file, any step not run, every MISSING line and the checks that could not run.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Every opportunity has a quote or a count behind it, or is marked GUESS.
• The roadmap lists outcomes, each with a measure, a start, a target and one owner. Features are examples only.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Marty Cagan would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Map the opportunities. Finds the customer problems under each outcome from your evidence, marks any without evidence as a guess, and adds solution ideas under the top ones.
• Build the roadmap. Lists outcomes with a measure, an owner and bets, in Marty Cagan's manner. Old features go under an outcome or are listed as unowned.
• Plan the quarter. Picks the bets that fit your capacity, sets what each should move and how you will know, and lists what you are not doing.
• Write the update. Writes the stakeholder update in plain words from the roadmap and the plan, without dates the plan does not hold.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id build-an-outcome-based-roadmap-and-write-the-update only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/build-an-outcome-based-roadmap-and-write-the-update/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The outcomes the business needs this year, as a number now and a target
• What you know about customers: tickets, reviews, survey answers or interview notes
• Your team's capacity for the quarter, in people and weeks
• Your current roadmap (optional)
• Last quarter's plan and results (optional)

Helpful context (optional)

• Customer interview notes
• Support ticket exports by theme
• Last quarter's results against its plan

Tools and access

• Any good chat AI: Every step is a plan or a piece of writing.
• A whiteboard or diagram tool: The opportunity tree is easier to argue with when you can see it.
• Any good chat AI: Sorting and rewriting a list is text work that any strong chat AI does with this skill.
• A spreadsheet: Holds the result numbers you track at each review point.
• Claude or ChatGPT: Either can write the updates. Neither can read your git history, so paste the commits or run the script yourself.
• Git and Python 3: Needed only if you want the changelog script to read your git history.

Functions and deliverables

• Quarterly product roadmap planner: Link customer problems to product goals, choose work for the quarter and draft an update explaining the choices.
  • An opportunity tree: the customer problems under each outcome, each with its evidence
  • An outcome roadmap with a measure, an owner and bets under each outcome
  • A list of old roadmap features that have no outcome behind them
  • A quarter plan with the bets, what each should move, how you will know and what you are not doing
  • A one-page update for stakeholders
• Opportunity solution tree builder: Share the outcome you want. Get a tree of customer opportunities, solution ideas and the tests for each.
  • A four-level tree from outcome to experiments
  • Ranked customer opportunities
  • Several solution ideas per opportunity
  • Cheap tests for the top ideas
  Source: Pawel Huryn.
• Product outcome roadmap planner: Turn a feature roadmap into outcomes. Paste your features and dates. Get three to five customer problems, each with a result you can measure.
  • Each item marked as a feature, a problem or a result
  • Three to five problems, each for a named customer
  • One measurable result per problem
  • Review points in place of dates, with the evidence each needs
• Quarterly roadmap builder: Turn your backlog and requests into a quarterly roadmap that balances new builds, fixes and upkeep, with a not-doing list you can defend.
  • Roadmap by quarter and theme
  • Ranking with reasons
  • Dependency map
  • Not-doing list
  • Version for stakeholders
  Source: RampStack.
• Roadmap update writer: Turn your product plans into a roadmap update for executives, engineers or customers. Get the roadmap story, release notes or a changelog, one per reader.
  • A roadmap in the format that fits how certain your plans are
  • One update for each reader you named
  • Customer-facing or internal release notes
  • A changelog grouped by type of change
  • A list of details you still need to supply
  Source: Alireza Rezvani.
• Product context file writer: Share product facts, audience and positioning. Get a reviewed context file that other marketing skills can reference.
  • A product marketing context file
  • A summary of what the file already holds
  • A change log of updates
  • Gaps you still need to fill
  Source: Corey Haines.
• Marty Cagan: Review a product idea using Marty Cagan’s recorded approach. Test its value, ease of use, build limits and fit with the business.
  • Your problem worked on the way Marty Cagan would: their questions, their method, their push-back
  • The answer or the work, in Marty Cagan's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• Your roadmap has twenty features and no one can say what each is for.
• You ship on time and the numbers do not move.
• Stakeholders keep adding features and you need a way to say no with a reason.
• A new quarter starts and you must turn goals into a plan the team can commit to.

Limits to check before starting

• You need a yes or no on one feature request: use the Feature request screener.
• You have no customer evidence yet: collect some first with the Customer job interview planner, then come back.
• You only need a status update for work already under way: use the Roadmap update writer on its own.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the workflow pack and add it to Claude, ChatGPT or Gemini. Use your strongest model.
• Paste your outcomes with the number now and the target. Add tickets, reviews or notes, and your capacity.
• Say: Follow the workflow, and mark anything you cannot find in what I gave you as MISSING.
• Check the opportunity tree first. Every problem needs a quote or a count behind it. Remove any that do not have one.
• Read the quarter plan with your team. Cut any bet you would not make.
• Read the update once as a stakeholder, then send it yourself. The AI sends nothing.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/build-an-outcome-based-roadmap-and-write-the-update for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.